Analyzing Patterns of Violence Against Women in Pernambuco Using Self-Organizing Maps and Apriori Algorithm
Brenda Barros Alves Da Silva, Rodolfo Moreira Pereira, Cleyton Mário de Oliveira Rodrigues, Roberta Fagundes · 2024
This study investigates significant patterns of violence against women in Pernambuco using Self-Organizing Maps (SOM) and the Apriori algorithm. The methodology includes trend analysis, clustering, and association rule mining, utilizing data from the Ministério da Mulher covering 2015 to 2021. The exploratory data analysis identified demographic, temporal, and spatial trends in violence. SOM was employed for dimensionality reduction and clustering, revealing three clusters representing 5.24%, 19.68%, and 75.08% of the dataset, respectively. The Apriori algorithm was applied to yearly subsets of each cluster to uncover relevant association patterns. Our findings highlight key characteristics and temporal dynamics of violence, supporting the development of targeted interventions and support systems.